> ## AI Agent Context
> Get the complete documentation index at: https://aistudio.google.com/docs/llms.txt
> Use this file to discover all available pages.
> For the full documentation in a single file, fetch: https://aistudio.google.com/docs/llms-full.txt

# Context caching

In a typical AI workflow, you might pass the same input tokens over and over to
a model. The Gemini API offers implicit caching to optimize performance and
costs.

{% callout type="note" %}
  The **Interactions API** only supports implicit caching. Explicit caching
  (manually creating and managing cache objects) is not supported in the
  Interactions API, or for Gemini 4 Argon and onward. To use explicit caching on
  supported Gemini 3 and 2.5 models, switch to the
  [generateContent API](/docs/caching?generate-content=true).

{% /callout %}

## Implicit caching  {% id="implicit-caching" %}

Implicit caching is enabled by default for all Gemini 2.5 and newer models. It is
supported for both [stateful](/docs/text-generation#multi-turn-conversations) (using `previous_interaction_id`)
and [stateless](/docs/text-generation#stateless-conversations) conversation modes.
We automatically pass on cost savings if your request hits caches. You don't need to configure anything to turn it on. The following table lists the minimum input token count for each model:

| Model | Min token limit |
| :--- | :--- |
| Gemini 4 Argon | 4,096 |
| Gemini 3.8 Flash | 4,096 |
| Gemini 3.6 Flash | 4,096 |
| Gemini 3.1 Pro Preview | 4,096 |
| Gemini 2.5 Flash | 2,048 |
| Gemini 2.5 Pro | 2,048 |

To increase the chance of an implicit cache hit:

- Try putting large and common contents at the beginning of your prompt
- Try to send requests with similar prefix in a short amount of time

{% callout type="note" %}
  **Multi-turn and agent loops on Gemini 4 (Argon and newer):** Gemini caches the
  full previous request only if the new request adds at least 2,050 tokens. Model
  output, thought, and function results all count toward this total. For smaller
  additions, Gemini re-processes the last 2,050 tokens of the previous request at
  the standard input rate. Most agent turns exceed this threshold.

{% /callout %}

You can see the number of tokens which were cache hits in the response object's
`usage.total_cached_tokens` (Python and JavaScript) field.